GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision

arXiv:2405.10591v1 Announce Type: new
Abstract: 3D occupancy perception holds a pivotal role in recent vision-centric autonomous driving systems by converting surround-view images into integrated geometric and semantic representations within dense 3D grids. Nevertheless, current models still encounter two main challenges: modeling depth accurately in the 2D-3D view transformation stage, and overcoming the lack of generalizability issues due to sparse LiDAR supervision. To address these issues, this paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception. Our approach …

abstract arxiv autonomous autonomous driving autonomous driving systems challenges cs.cv current driving fusion images modeling network perception pivotal role semantic supervision systems type view vision